© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2224
    Prev
    Next
    INDEX
    Explanations

    say net/num

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    段
    -17.88
    cmds
    -17.63
    排列
    -17.50
    simulate
    -16.50
    定
    -16.50
    ussions
    -16.00
     đoạn
    -16.00
    _quant
    -15.94
     khảo
    -15.75
    inking
    -15.13
    POSITIVE LOGITS
     net
    47.75
     Net
    42.75
    net
    42.00
     num
    41.50
    num
    40.00
    Net
    39.00
    =num
    37.25
    (net
    36.25
    [num
    35.75
     nets
    35.75
    Activations Density 0.206%

    No Known Activations